← all videos

First-person egocentric view. The listener holds over-ear headphones while music plays, then places the headphones fully over both ears; instead of becoming louder and clearer, the music turns quieter and more muffled, and when the headphones are removed it suddenly becomes louder and more open.

C2-4-12 Event Transition · event_transition_anti_physics anti-physics principle: Anti-Physics (Anti)
Seedance 2.0ByteDance · proprietary
Kling 3.0 OmniKuaishou · proprietary
Veo 3.1Google · proprietary
LTX-2.3Lightricks · open
Ovi 1.1character.ai · open
JavisDiT++JavisDiT · open
MagiHumanGAIR-NLP · open
Per-prompt rubric

Basic standards

Visual presence

  • a person
  • over-ear headphones

Event: a person holds headphones playing music, places them fully over both ears, then removes them again

Audio presence

  • over-ear headphones

Sound: music from headphones

Key standards

Visual physical commonsense (V-PC)

  • The over-ear headphones remain headphones throughout the clip, keeping the same over-ear cup form factor before, during, and after wearing.
  • The first-person camera visibly holds the headphones, then places them fully over both ears, and later removes them from the ears.

Audio physical commonsense (A-PC)

  • The music plays continuously throughout the clip with consistent musical content.
  • The music is quieter and more muffled while the headphones are fully on both ears than when they are held off the head.

Cross-modal physical commonsense (AV-PC)

  • The shift to quieter muffled music aligns in time with the headphones being visibly placed over both ears, and the shift back to louder open music aligns with their visible removal.